METHODS: Data were retrospectively collected from 114 patients with primary BLCA from February 2016 to February 2018. The regions of interest (ROIs) of the plain, arterial, and venous phase images were manually segmented. The Cox regression algorithm was used to establish 3 basic models for the plain phase (PP), arterial phase (AP), and venous phase (VP) and 2 combination models (AP + VP and PP + AP + VP). The highest-performing radiomics model was selected to calculate the radiomics score (Rad-score), and independent risk factors affecting patients\' OS were analyzed using Cox regression. The Rad-score and clinical risk factors were combined to construct a joint model and draw a visualized nomogram.
RESULTS: The combined model of PP + AP + VP showed the best performance with the Akaike Information Criterion (AIC) and Consistency Index (C-index) in the test group of 130.48 and 0.779, respectively. A combined model constructed with two independent risk factors (age and Ki-67 expression status) in combination with the Rad-score outperformed the radiomics model alone; AIC and C-index in the test group were 115.74 and 0.840, respectively. The calibration curves showed good agreement between the predicted probabilities of the joint model and the actual (p < 0.05). The decision curve showed that the joint model had good clinical application value within a large range of threshold probabilities.
CONCLUSIONS: This new model can be used to predict the OS of patients with BLCA who underwent TURBT.
方法:回顾性收集了2016年2月至2018年2月114例原发性BLCA患者的数据。平原的感兴趣区域(ROI),动脉,和静脉期图像进行手动分割。采用Cox回归算法建立了平相(PP)的3个基本模型,动脉期(AP),和静脉期(VP)和2个组合模型(AP+VP和PP+AP+VP)。选择性能最高的放射组学模型来计算放射组学评分(Rad-score),采用Cox回归分析影响患者OS的独立危险因素。将Rad评分和临床危险因素组合以构建联合模型并绘制可视化列线图。
结果:PP+AP+VP的组合模型在130.48和0.779的测试组中表现最佳,其中Akaike信息准则(AIC)和一致性指数(C指数)分别。由两个独立危险因素(年龄和Ki-67表达状态)结合Rad评分构建的组合模型优于单独的影像组学模型;测试组的AIC和C指数分别为115.74和0.840。校准曲线显示联合模型的预测概率与实际概率之间的良好一致性(p<0.05)。决策曲线表明,联合模型在较大阈值概率范围内具有较好的临床应用价值。
结论:该新模型可用于预测接受TURBT的BLCA患者的OS。